Recent advances in statistical-computational theory for PDE models

Thumbnail

Event details

Date 22.09.2026
Hour 16:15
Speaker Sven Wang (EPFL)
Location
Category Conferences - Seminars
Event Language English

We present recent statistical and computational guarantees which underpin methodologies for parameter inference in complex statistical models, for instance arising from differential equations (PDEs/SDEs). Firstly, we will discuss statistical convergence guarantees with growing statistical sample size. Secondly, we address recent progress in studying the (polynomial) computational complexity of the numerical algorithms required. This includes polynomial-time mixing results for high-dimensional Markov Chain Monte Carlo (MCMC) methods as well as recent “generalized M-estimators” achieving near-linear runtime with respect to the statistical sample size N.
 

Practical information

  • General public
  • Free

Organizer

  • Prof. Nicolas Boumal

Contact

  • Nicolas Boumal Séverine Eggli

Event broadcasted in

Share